cloud-penetration-testing

This skill should be used when the user asks to "perform cloud penetration testing", "assess Azure or AWS or GCP security", "enumerate cloud resources", "exploit cloud misconfigurations", "test O365 security", "extract secrets from cloud environments", or "audit cloud infrastructure". It provides comprehensive techniques for security assessment across major cloud platforms.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A comprehensive, highly actionable cloud-pentesting reference with excellent executable commands and structure. Weaknesses are repetition affecting conciseness and absence of validation checkpoints for destructive/batch operations, which caps workflow clarity.

Suggestions

Add explicit validation/verification checkpoints after destructive or batch operations (e.g., confirm a created access key works, verify exfiltrated data integrity) to lift workflow clarity above 3.

De-duplicate commands that appear in both the phase walkthroughs and the Quick Reference tables to improve token efficiency.

Move the per-platform 'Useful Tools' and metadata-URL tables into the existing references file, keeping SKILL.md as a tighter overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command listings, but the ~500-line body repeats commands across phases and Quick Reference tables, and includes minor over-explanation (e.g., 'may bypass MFA', 'may contain secrets') that pads the token budget.	3 / 5
Actionability	Fully executable, copy-paste ready commands across all three platforms with concrete examples covering common cases; code blocks are complete rather than pseudocode.	5 / 5
Workflow Clarity	Steps are clearly sequenced into 11 phases, but for destructive/batch operations (key creation, password spray, VM command execution, data exfiltration) there are no validation checkpoints or feedback loops, capping this dimension at 3 per the destructive-operations rule.	3 / 5
Progressive Disclosure	Good structure with clear sections, quick-reference tables, and a single one-level-deep reference ([references/advanced-cloud-scripts.md]) that exists as a real file; minor gaps as some reference-worthy material (e.g., tool table) could be split out.	4 / 5
	Total	15 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit 'when' trigger guidance and concrete action terms across the cloud-pentesting niche. Minor specificity gap as it omits persistence/privilege-escalation actions found in the body.

Suggestions

Consider trimming the long list of quoted triggers slightly; the redundancy between 'perform cloud penetration testing' and 'audit cloud infrastructure' could be tightened without losing trigger coverage.

Add a concrete action term such as 'privilege escalation' or 'establish persistence' to round out the capability coverage beyond enumeration and extraction.

Dimension	Reasoning	Score
Specificity	Names concrete actions via the quoted trigger phrases 'enumerate cloud resources', 'exploit cloud misconfigurations', and 'extract secrets from cloud environments', plus 'security assessment', giving several specific actions with minor coverage gaps (no explicit mention of persistence or privilege escalation).	4 / 5
Completeness	Explicitly answers both 'what' ('provides comprehensive techniques for security assessment across major cloud platforms') and 'when' ('should be used when the user asks to...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms users would say: 'perform cloud penetration testing', 'assess Azure or AWS or GCP security', 'test O365 security', 'audit cloud infrastructure', covering synonyms and platform names.	5 / 5
Distinctiveness Conflict Risk	Clear niche of cloud penetration testing with named platforms (Azure/AWS/GCP/O365) and distinct trigger phrases, minimizing conflict with generic security skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (502 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/cloud-penetration-testing/SKILL.md
Commit: 8428a63

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.